agentmods.dev

copilot-sdk copilot-instructions.md

Repository guidance for the GitHub Copilot SDK, a set of language libraries that connects applications to the Copilot command-line program. It explains the codebase structure, common commands, and tests in this monorepo, a repository containing several related projects.

In plain words
What is it for?
Finding important files, building and testing SDK changes, adding end-to-end tests, and working with the JSON-RPC connection between the SDKs and Copilot CLI.
Why use it?
It gives contributors and coding agents a clear starting point for understanding the repository and working consistently across its language implementations.

Instructions file for GitHub Copilot

10k 2d ago A scan 1,801 tokens original MIT
View the source file github/copilot-sdk
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/github/copilot-sdk/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/github/copilot-sdk

Made for: GitHub Copilot.

Per session 1,801 This file is loaded in full into every session.
When invoked 1,801 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01801 $0.01801
Opus 5 $0.00901 $0.00901
Sonnet 5 $0.00360 $0.00360
Haiku 4.5 $0.00180 $0.00180

Measured yesterday against content hash cb5d8f000386, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-sdk copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/copilot-instructions.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot SDK — Assistant Instructions

Quick purpose: Help contributors and AI coding agents quickly understand this mono-repo and be productive (build, test, add SDK features, add E2E tests). ✅

Big picture 🔧

  • The repo implements language SDKs (Node/TS, Python, Go, .NET, Rust, Java) that speak to the Copilot CLI via JSON‑RPC (see README.md and nodejs/src/client.ts).
  • Typical flow: your App → SDK client → JSON-RPC → Copilot CLI (server mode). The CLI must be installed or you can connect to an external CLI server via the CLI URL option (language-specific casing) (Node: cliUrl, Go: CLIUrl, .NET: CliUrl, Python: cli_url, Java: cliUrl).

Most important files to read first 📚

  • Top-level: README.md (architecture + quick start)
  • Language entry points: nodejs/src/client.ts, python/README.md, go/README.md, dotnet/README.md
  • Java: java/README.md, java/pom.xml, java/sdk/pom.xml, java/copilot-native/pom.xml
  • Test harness & E2E: test/harness/*, Python harness wrapper python/e2e/testharness/proxy.py
  • Schemas & type generation: nodejs/scripts/generate-session-types.ts
  • Session snapshots used by E2E: test/snapshots/ (used by the replay proxy)
  • Docs style guide: .github/instructions/docs-style.instructions.md (used for docs/**)

Developer workflows (commands you’ll use often) ▶️

  • Monorepo helpers: use just tasks from repo root:
    • Install deps: just install (runs npm ci, uv pip install -e, go mod download, dotnet restore)
    • Format all: just format | Lint all: just lint | Test all: just test
  • Per-language:
    • Node: cd nodejs && npm ci → npm test (Vitest), npm run generate:session-types to regenerate session-event types
    • Python: cd python && uv pip install -e . --group dev → uv run pytest (E2E tests use the test harness)
    • Go: cd go && go test ./...
    • .NET: cd dotnet && dotnet test test/GitHub.Copilot.SDK.Test.csproj
    • .NET testing note: Never add InternalsVisibleTo to any project file when writing tests. Tests must only access public APIs.
    • Java: cd java && mvn clean verify (full build + tests), mvn spotless:apply (format code before commit)
    • Java single test: cd java && mvn test -Dtest=CopilotClientTest | single method: mvn test -Dtest=ToolsTest#testToolInvocation
    • Java format check only: mvn spotless:check | Build without tests: mvn clean package -DskipTests
    • Java testing note: Always use mvn verify without -q and without piping through grep. Never add InternalsVisibleTo equivalent — tests must only access public APIs.
  • Use configured LSPs for supported operations like finding references instead of pattern matching, renaming symbols, etc.

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 74 lines · 1,801 tokens per session scan A cb5d8f000386

Subscribe to this mod's changes

copilot-sdk copilot-instructions.md is an instructions file published in the GitHub repository github/copilot-sdk (10,441 stars, last pushed 2d ago), licensed MIT. It adds 1,801 tokens to every session, about $0.0090 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Testing
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens